{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:35:37Z","timestamp":1760243737760,"version":"build-2065373602"},"reference-count":22,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2012,12,4]],"date-time":"2012-12-04T00:00:00Z","timestamp":1354579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Recent studies have shown that the Gibbs density function is a good model for visual patterns and that its parameters can be learned from pattern category training data by a gradient algorithm optimizing a constrained entropy criterion. These studies represented each pattern category by a single density. However, the patterns in a category can be so complex as to require a representation spread over several densities to more accurately account for the shape of their distribution in the feature space. The purpose of the present study is to investigate a representation of visual pattern category by several Gibbs densities using a Kohonen neural structure. In this Gibbs density based Kohonen network, which we call a Gibbsian Kohonen network, each node stores the parameters of a Gibbs density. Collectively, these Gibbs densities represent the pattern category. The parameters are learned by a gradient update rule so that the corresponding Gibbs densities maximize entropy subject to reproducing observed feature statistics of the training patterns. We verified the validity of the method and the efficiency of the ensuing Gibbs density pattern representation on a handwritten character recognition application.<\/jats:p>","DOI":"10.3390\/e14122478","type":"journal-article","created":{"date-parts":[[2012,12,4]],"date-time":"2012-12-04T15:10:18Z","timestamp":1354633818000},"page":"2478-2491","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Maximum Entropy Gibbs Density Modeling for Pattern Classification"],"prefix":"10.3390","volume":"14","author":[{"given":"Neila","family":"Mezghani","sequence":"first","affiliation":[{"name":"Laboratoire de recherche en imagerie et orthop\u00e9die, Centre de recherche du CHUM, \u00c9cole de technologie sup\u00e9rieure, Pavillon J.A. de S\u00e8ve, 1560, rue Sherbrooke E., Y-1615, Montreal (QC),H2L 4M1, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amar","family":"Mitiche","sequence":"additional","affiliation":[{"name":"Institut national de la recherche scientifique, INRS-EMT, Place Bonaventure, 800, de La Gaucheti\u00e8re O., Montreal (QC), H5A 1K6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Cheriet","sequence":"additional","affiliation":[{"name":"\u00c9cole de technologie sup\u00e9rieure, 1100, Rue Notre-Dame O., Montreal (QC), H3C 1K3, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2012,12,4]]},"reference":[{"key":"ref_1","unstructured":"Duda, P.O., Hart, P.E., and Stork, D.G. (2001)."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/34.824819","article-title":"Statistical pattern recognition: A review","volume":"22","author":"Jain","year":"2000","journal-title":"IEEE Trans. Pattern Recognit. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/34.809110","article-title":"Embedding gestalt laws in Markov random fields","volume":"21","author":"Zhu","year":"1999","journal-title":"IEEE Trans. Pattern Recognit. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1109\/34.632983","article-title":"Prior learning and Gibbs reaction-diffusion","volume":"19","author":"Zhu","year":"1997","journal-title":"IEEE Trans. Pattern Recognit. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1162\/neco.1997.9.8.1627","article-title":"Minimax entropy principle and its application to texture modeling","volume":"9","author":"Zhu","year":"1997","journal-title":"Neural Comput."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1023\/A:1007925832420","article-title":"Filters, Random Fields and Maximum Entropy (FRAME): Towards a unified theory for texture modeling","volume":"27","author":"Zhu","year":"1998","journal-title":"Int. J. Comput. Vision"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mezghani, N., Mitiche, A., and Cheriet, M. (2008). Bayes classification of online arabic characters by Gibbs modeling of class conditional densities. IEEE Trans. Pattern Recognit. Mach. Intell., 30.","DOI":"10.1109\/TPAMI.2007.70753"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kohonen, T. (1995). Self-organizing Maps, Springer.","DOI":"10.1007\/978-3-642-97610-0"},{"key":"ref_9","first-page":"102","article-title":"Bibliography of Self-Organizing Map SOM papers: 1981\u20131997","volume":"1","author":"Kaski","year":"1998","journal-title":"Neural Comput. Surveys"},{"key":"ref_10","first-page":"1","article-title":"Bibliography of Self-Organizing Map SOM papers: 1998\u20132001 addendum","volume":"3","author":"Oja","year":"2003","journal-title":"Neural Comput. Surveys"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MASSP.1987.1165576","article-title":"An introduction to computing with neural networks","volume":"3","author":"Lippman","year":"1987","journal-title":"IEEE ASSP Mag."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ritter, H., and Schulten, K. (,  1988). 1988. Kohonen Self-Organizing Maps: Exploring Their Computational Capabilities. Proceedings of the IEEE International Joint Conference on Neural Networks, Piscataway, NJ, USA. IEEE Service Center.","DOI":"10.1109\/ICNN.1988.23838"},{"key":"ref_13","first-page":"529","article-title":"Quantification vectorielle d\u2019images par le r\u00e9seau neuronal de kohonen","volume":"6","author":"LeBail","year":"1989","journal-title":"Traitement du Signal"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/0893-6080(93)90021-N","article-title":"Modeling and classification of shape using a Kohonen associative memory with selective multiresolution","volume":"6","author":"Sabourin","year":"1993","journal-title":"Neural Netw."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/S0925-2312(98)00026-5","article-title":"Probabilistic self-organizing map and radial basis function","volume":"20","author":"Anouar","year":"1998","journal-title":"J. Neurocomput."},{"key":"ref_16","unstructured":"Mezghani, N., Mitiche, A., and Cheriet, M. (2002, January 6\u20138). On-line Recognition of Handwritten Arabic Characters Using a Kohonen Neural Network. Proceedings of the 8th International Workshop on Frontiers in Handwriting Recognition, Niagara-on-the-Lake, Canada."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s10032-005-0145-8","article-title":"A new representation of shape and its use for superior performance in on-line Arabic character recognition by an associative memory","volume":"7","author":"Mezghani","year":"2005","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1142\/S0218001496000268","article-title":"Pattern category assignement by neural networks and the nearest neighbors rule","volume":"10","author":"Mitiche","year":"1996","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Descombes, X., Morris, R., Zerubia, J., and Berthod, M. (1998, January 21\u201323). Maximum Likelihood Estimation of Markov Random Field Parameters Using Markov Chain Monte Carlo Algorithms. Proceedings of the Internalional Workshop on Energy Minimization Methods, Venice, Italy.","DOI":"10.1007\/3-540-62909-2_77"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/BF00203171","article-title":"Self-organizing semantic maps","volume":"61","author":"Ritter","year":"1989","journal-title":"Biol. Cybern."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11548-011-0667-0","article-title":"A Kohonen neural network description of scoliosis fused region and their corresponding lenke classification","volume":"7","author":"Mezghani","year":"2012","journal-title":"Int. J. Comput. Assist. Radiol. Surgery"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MCS.2003.1188770","article-title":"Estimation via Markov Chain Monte Carlo","volume":"23","author":"Spall","year":"2003","journal-title":"IEEE Control Syst. Mag."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/14\/12\/2478\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:54:00Z","timestamp":1760219640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/14\/12\/2478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12,4]]},"references-count":22,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2012,12]]}},"alternative-id":["e14122478"],"URL":"https:\/\/doi.org\/10.3390\/e14122478","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2012,12,4]]}}}